public void printDocumentTopics(PrintWriter pw, double threshold, int max) {
pw.println("#doc source topic proportion ...");
int docLen;
double topicDist[] = new double[topics.length];
for (int di = 0; di < topics.length; di++) {
pw.print(di);
pw.print(' ');
if (ilist.get(di).getSource() != null) {
pw.print(ilist.get(di).getSource().toString());
} else {
pw.print("null-source");
}
pw.print(' ');
docLen = topics[di].length;
for (int ti = 0; ti < numTopics; ti++)
topicDist[ti] = (((float) docTopicCounts[di][ti]) / docLen);
if (max < 0) max = numTopics;
for (int tp = 0; tp < max; tp++) {
double maxvalue = 0;
int maxindex = -1;
for (int ti = 0; ti < numTopics; ti++)
if (topicDist[ti] > maxvalue) {
maxvalue = topicDist[ti];
maxindex = ti;
}
if (maxindex == -1 || topicDist[maxindex] < threshold) break;
pw.print(maxindex + " " + topicDist[maxindex] + " ");
topicDist[maxindex] = 0;
}
pw.println(' ');
}
}
public static void main(String[] args) throws Exception {
InstanceList instances = InstanceList.load(new File(args[0]));
int numTopics = Integer.parseInt(args[1]);
ParallelTopicModel model = new ParallelTopicModel(numTopics, 5.0, 0.01);
model.addInstances(instances);
model.setNumIterations(1000);
model.estimate();
TopicModelDiagnostics diagnostics = new TopicModelDiagnostics(model, 20);
if (args.length == 3) {
PrintWriter out = new PrintWriter(args[2]);
out.println(diagnostics.toXML());
out.close();
}
}
public TestCRFPipe(String trainingFilename) throws IOException {
ArrayList<Pipe> pipes = new ArrayList<Pipe>();
PrintWriter out = new PrintWriter("test.out");
int[][] conjunctions = new int[3][];
conjunctions[0] = new int[] {-1};
conjunctions[1] = new int[] {1};
conjunctions[2] = new int[] {-2, -1};
pipes.add(new SimpleTaggerSentence2TokenSequence());
// pipes.add(new FeaturesInWindow("PREV-", -1, 1));
// pipes.add(new FeaturesInWindow("NEXT-", 1, 2));
pipes.add(new OffsetConjunctions(conjunctions));
pipes.add(new TokenTextCharSuffix("C1=", 1));
pipes.add(new TokenTextCharSuffix("C2=", 2));
pipes.add(new TokenTextCharSuffix("C3=", 3));
pipes.add(new RegexMatches("CAPITALIZED", Pattern.compile("^\\p{Lu}.*")));
pipes.add(new RegexMatches("STARTSNUMBER", Pattern.compile("^[0-9].*")));
pipes.add(new RegexMatches("HYPHENATED", Pattern.compile(".*\\-.*")));
pipes.add(new RegexMatches("DOLLARSIGN", Pattern.compile("\\$.*")));
pipes.add(new TokenFirstPosition("FIRSTTOKEN"));
pipes.add(new TokenSequence2FeatureVectorSequence());
pipes.add(new SequencePrintingPipe(out));
Pipe pipe = new SerialPipes(pipes);
InstanceList trainingInstances = new InstanceList(pipe);
trainingInstances.addThruPipe(
new LineGroupIterator(
new BufferedReader(
new InputStreamReader(new GZIPInputStream(new FileInputStream(trainingFilename)))),
Pattern.compile("^\\s*$"),
true));
out.close();
}
public void printState(PrintWriter pw) {
Alphabet a = ilist.getDataAlphabet();
pw.println("#doc pos typeindex type topic");
for (int di = 0; di < topics.length; di++) {
FeatureSequence fs = (FeatureSequence) ilist.get(di).getData();
for (int si = 0; si < topics[di].length; si++) {
int type = fs.getIndexAtPosition(si);
pw.print(di);
pw.print(' ');
pw.print(si);
pw.print(' ');
pw.print(type);
pw.print(' ');
pw.print(a.lookupObject(type));
pw.print(' ');
pw.print(topics[di][si]);
pw.println();
}
}
}
public void printState(File f) throws IOException {
PrintWriter writer = new PrintWriter(new FileWriter(f));
printState(writer);
writer.close();
}
public void printState(PrintWriter pw) {
pw.println("#doc pos typeindex type bigrampossible? topic bigram");
for (int di = 0; di < topics.length; di++) {
FeatureSequenceWithBigrams fs = (FeatureSequenceWithBigrams) ilist.get(di).getData();
for (int si = 0; si < topics[di].length; si++) {
int type = fs.getIndexAtPosition(si);
pw.print(di);
pw.print(' ');
pw.print(si);
pw.print(' ');
pw.print(type);
pw.print(' ');
pw.print(uniAlphabet.lookupObject(type));
pw.print(' ');
pw.print(fs.getBiIndexAtPosition(si) == -1 ? 0 : 1);
pw.print(' ');
pw.print(topics[di][si]);
pw.print(' ');
pw.print(grams[di][si]);
pw.println();
}
}
}